© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 89692
    Prev
    Next
    INDEX
    Explanations

    Composable abstraction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ↵
    0.42
     etc
    0.40
     gleiche
    0.38
     stejně
    0.38
    ifiers
    0.37
    kyo
    0.36
    uto
    0.36
    tool
    0.36
     planar
    0.35
     optimally
    0.35
    POSITIVE LOGITS
     பெரும்பாலும்
    0.52
    钀
    0.47
    ခဲ့
    0.47
    愆
    0.47
    鎸
    0.47
    beqz
    0.46
     defray
    0.45
    洧
    0.45
    มาก
    0.45
    შინ
    0.44
    Activations Density 0.017%

    No Known Activations